Loading video...

Video Failed to Load

Go Home

Introducing pixelSplat: feed-forward Gaussian splats from image pairs! Led by David Charatan and Lester Li, collaborating with Andrea Tagliasacchi @CVPR! We propose a memory-efficient, fast and editable alternative to pixelNeRF based on 3D Gaussian Splatting! 1/n

vincesitzmann's profile picture

Vincent Sitzmann

19,168 subscribers

47,594 views • 2 years ago •via X (Twitter)

Science & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.
0:16

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.

MrNeRF

14,229 views • 1 year ago

Testing InstantSplat with a few frames from Oppenheimer, super fast 3D Gaussian Splatting
0:12

Testing InstantSplat with a few frames from Oppenheimer, super fast 3D Gaussian Splatting

Radamés Ajna

48,871 views • 2 years ago

More experiments with gaussian splats and AR image targets
0:10

More experiments with gaussian splats and AR image targets

Ian Curtis

10,735 views • 1 year ago

Playing with SuperSplat v2.16 for editing and combining gaussian splats. Very fast & easy to use, open source, and web based! PlayCanvas #GaussianSplatting
0:19

Playing with SuperSplat v2.16 for editing and combining gaussian splats. Very fast & easy to use, open source, and web based! PlayCanvas #GaussianSplatting

Jason Key

68,602 views • 7 months ago

3D Gaussian Splatting with Unity VFX Graph
0:11

3D Gaussian Splatting with Unity VFX Graph

Keijiro Takahashi

135,059 views • 2 years ago

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.
0:12

Apple just trained a 3D Gaussian head reconstruction model on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.

KIRI Engine - 3D Scanner App

12,125 views • 1 month ago

📢We introduce “RefFusion”, a novel inpainting method for scenes reconstructed using 3D Gaussian Splatting. 🔗 TLDR: we personalize an image diffusion model to a given reference image and distill its knowledge to 3D through score distillation sampling.
0:11

📢We introduce “RefFusion”, a novel inpainting method for scenes reconstructed using 3D Gaussian Splatting. 🔗 TLDR: we personalize an image diffusion model to a given reference image and distill its knowledge to 3D through score distillation sampling.

Ashkan Mirzaei

34,700 views • 2 years ago

NeuralGS Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations
0:10

NeuralGS Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations

AK

68,496 views • 1 year ago

I made a 3D Gaussian Splatting renderer for WebGL! The following scene renders 1.3M splats in real time. I wanted to understand a bit more how gaussian splats were rasterized, reimplementing the original paper seemed to be the best approach. I will publish it on github soon!
0:17

I made a 3D Gaussian Splatting renderer for WebGL! The following scene renders 1.3M splats in real time. I wanted to understand a bit more how gaussian splats were rasterized, reimplementing the original paper seemed to be the best approach. I will publish it on github soon!

kishimisu

84,532 views • 2 years ago

yoooooo.... 3D gaussian splatting + simulated kinematics
0:10

yoooooo.... 3D gaussian splatting + simulated kinematics

David Marx (@digthatdata.bsky.social)

73,071 views • 2 years ago

LGTM from Apple: 4K feed-forward 3D Gaussian Splatting. instant 4K 3D scenes without massive GPUs.. - predicts a few lightweight 3D shapes, wraps them in ultra-high-res 2D textures. - low Memory usage You take two normal photos of a room. Instantly walk around it in flawless 3D.
0:12

LGTM from Apple: 4K feed-forward 3D Gaussian Splatting. instant 4K 3D scenes without massive GPUs.. - predicts a few lightweight 3D shapes, wraps them in ultra-high-res 2D textures. - low Memory usage You take two normal photos of a room. Instantly walk around it in flawless 3D.

Wildminder

46,278 views • 3 months ago

Gaussian Painters imported into #b3d as ellipsoids (3D Gaussian Splatting plugin for Blender - work in progress)
0:19

Gaussian Painters imported into #b3d as ellipsoids (3D Gaussian Splatting plugin for Blender - work in progress)

Alex Carlier

156,174 views • 2 years ago

Tune in @ ICCV on Mon @ 10.30am where I talk about everything 3D + Realism: - Hyperscape: Gaussian Splatting in VR - FlowR: Flowing from Sparse-2-Dense 3D Recon - BulletGen: Improving 4D Recon with Bullet-Time Gen - MapAnything: Universal Feed-Forward Metric 3D Recon 🧵👇
0:12

Tune in @ ICCV on Mon @ 10.30am where I talk about everything 3D + Realism: - Hyperscape: Gaussian Splatting in VR - FlowR: Flowing from Sparse-2-Dense 3D Recon - BulletGen: Improving 4D Recon with Bullet-Time Gen - MapAnything: Universal Feed-Forward Metric 3D Recon 🧵👇

Jonathon Luiten

15,496 views • 8 months ago

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."
0:16

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."

MrNeRF

17,206 views • 1 year ago

The first public dynamic Gaussian Splatting implementation in VR is here from San Francisco based Gmix, compatible with WebXR and Apple Vision Pro. 🔗
0:17

The first public dynamic Gaussian Splatting implementation in VR is here from San Francisco based Gmix, compatible with WebXR and Apple Vision Pro. 🔗

Radiance Fields

31,612 views • 2 years ago

SplatVoxel: History-Aware Novel View Streaming without Temporal Training Contributions: • We propose a hybrid Splat-Voxel feed-forward reconstruction framework that leverages historical information to enable novel view streaming, without relying on multi-view video datasets for training. • We develop an efficient sparse voxel transformer with a coarse-to-fine voxel representation, outperforming existing feed-forward Gaussian splatting methods. • Experiment results demonstrate that our proposed framework enhances novel view synthesis for streaming scene reconstruction, providing better visual quality and reduced temporal artifacts through history-aware modeling.
0:18

SplatVoxel: History-Aware Novel View Streaming without Temporal Training Contributions: • We propose a hybrid Splat-Voxel feed-forward reconstruction framework that leverages historical information to enable novel view streaming, without relying on multi-view video datasets for training. • We develop an efficient sparse voxel transformer with a coarse-to-fine voxel representation, outperforming existing feed-forward Gaussian splatting methods. • Experiment results demonstrate that our proposed framework enhances novel view synthesis for streaming scene reconstruction, providing better visual quality and reduced temporal artifacts through history-aware modeling.

MrNeRF

10,823 views • 1 year ago

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.
0:14

PackUV: Packed Gaussian UV Maps for 4D Volumetric Video - PackUV — A new volumetric video representation that packs 3D Gaussian attributes into a sequence of UV atlases for efficient streaming and storage, making it readily compatible with existing video coding infrastructure. - PackUV-GS — An efficient method to fit PackUV directly from multiview videos using optical-flow-based keyframing and Gaussian labeling to handle large motions, disocclusions, and temporal consistency. - PackUV-2B — The largest multi-view 4D dataset with 2B frames, large motions, and disocclusions. It provides 360° coverage from 50+ synchronized cameras.

MrNeRF

17,035 views • 4 months ago

I implemented 3D Gaussian Splatting in WebGL. Check it out here:
0:17

I implemented 3D Gaussian Splatting in WebGL. Check it out here:

Kevin Kwok

168,875 views • 2 years ago

SuperSplat 2.19.0 is here! ✨ Your free and open source Gaussian Splat Editor 🎞️ Create videos of 4D Gaussian splats ➡️ Import support for SPZ and KSPLAT added 🌐 HTML viewer export now based on SOG ⌨️ New hotkeys for animation authoring [1 / 2]
0:12

SuperSplat 2.19.0 is here! ✨ Your free and open source Gaussian Splat Editor 🎞️ Create videos of 4D Gaussian splats ➡️ Import support for SPZ and KSPLAT added 🌐 HTML viewer export now based on SOG ⌨️ New hotkeys for animation authoring [1 / 2]

Will Eastcott

50,731 views • 5 months ago